Multi-agent Deep Reinforcement Learning in the Collision Avoidance Problem
Electronics and Control Systems · 06.03.2026 · 1 (87) · 57-62
DOI: 10.18372/1990-5548.87.20909 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics and Control Systems, online erschienen am 06.03.2026. Verfasst von Igor Yudenko.
Abstract (Originalsprache)
Obstacle avoidance is crucial for the succesfull completion of unmanned aerial vehicles missions. This article is devoted to the research of the multi-agent deep reinforcement learning in the collision avoidance problem. It is considered unmanned aerial vehicle swarms encounter diverse obstacles categorized into: static large-scale and small-scale obstacles, dynamic large-scale and small-scale obstacles, complex terrain, thin/low-visibility obstacles, partially-occluded/transparent obstacles. To address the abvove problem, a multi-agent deep reinforcement learning based trajectory control algorithm is proposed for managing the trajectory of each unmanned aerial vehicle independently. It was researched different approaches and multiple 3D simulation environments with help of reinforcement learning for the swarm of unmanned aerial vehicles.
Zitieren
APA
Yudenko, I. (2026). Multi-agent Deep Reinforcement Learning in the Collision Avoidance Problem. Electronics and Control Systems, 1(87), 57-62. https://doi.org/10.18372/1990-5548.87.20909
Vancouver
Yudenko I. Multi-agent Deep Reinforcement Learning in the Collision Avoidance Problem. Electronics and Control Systems. 2026;1(87):57-62. doi:10.18372/1990-5548.87.20909
BibTeX
@article{Yudenko2026,
author = {Yudenko, Igor},
title = {Multi-agent Deep Reinforcement Learning in the Collision Avoidance Problem},
journal = {Electronics and Control Systems},
year = {2026},
volume = {1},
number = {87},
pages = {57--62},
doi = {10.18372/1990-5548.87.20909}
}
EUVIMED